Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.
ObjectivesTo systematically review the efficacy of traditional Chinese medicine for arrhythmia caused by anthracycline drugs.MethodsPubMed, EMbase, The Cochrane Library, CBM, CNKI, WanFang Data databases were electronically searched to collect randomized controlled trials (RCTs) on the efficacy of traditional Chinese medicine for arrhythmia caused by anthracycline drugs from inception to October 2017. Two reviewers independently screened literature, extracted data and evaluated risk of bias of included studies. Meta-analysis was then performed by Revman 5.3 software.ResultsA total of 4 RCTs involving 312 patients were included. The results of meta-analysis showed that: the incidence of tachycardia in the Wenxin granule treatment group was lower than that in the control group (RR=0.35, 95%CI 0.18 to 0.67, P=0.002). Baoxinkang was more effective than antioxidant western medicine in protecting myocardial SOD activity (RR=2.25, 95%CI 1.74 to 2.76, P<0.000 01). But there was no significant difference between two groups on the incidence of atrial premature beats (RR=0.40, 95%CI 0.15 to 1.08,P=0.07), premature ventricular contractions (RR=0.56, 95%CI 0.23 to 1.34, P=0.19) and atrial fibrillation (RR=0.41, 95%CI 0.11 to 1.53, P=0.18). In addition, there was no significant difference between Wenxin granules and amiodarone in treating arrhythmia induced by anthracycline. The addition of Wenxin granules on the basis of anthracycline antitumor chemotherapy regimens was not effective in delaying disease progression compared with anthracycline alone. Wenxin granules could not change the SOD level of breast cancer patients with cardiotoxicity caused by anthracycline chemotherapy, compared with chemotherapy and basic treatment.ConclusionsThe current evidence shows that Wenxin granules can prevent and reduce anthracycline-induced tachycardia, but its efficacy in improving the overall efficiency, preventing and reducing atrial premature beats, premature ventricular contractions, atrial fibrillation, and SOD levels are unclear. Baoxinkang can protect myocardial SOD activity. Due to limited quality and quantity of the included studies, more high quality studies are required to verify above conclusions.
Atrial fibrillation is the most common arrhythmia in clinical practice, and catheter ablation has become a first-line treatment strategy. Among them, cryoballoon ablation has become a standardized treatment for atrial fibrillation due to its advantages such as short surgical time, short learning curve, and minimal patient pain. Currently, a large amount of clinical practice and research have provided new evidence for cryoballoon ablation as a first-line treatment for atrial fibrillation. Therefore, this article provides a review of the current status of catheter ablation, the current status, challenges faced, and prospects as a first-line catheter ablation strategy for atrial fibrillation of cryoballoon ablation, with the aim of providing reference for cardiologists in clinical decision-making in the initial rhythm control of atrial fibrillation.
ObjectiveTo analyze the perioperative safety and the short-term prognosis of non-small cell lung cancer (NSCLC) patients with preoperative arrhythmia. MethodsThe clinical data of NSCLC patients treated in the Department of Cardiothoracic Surgery, the First Affiliated Hospital of Chongqing Medical University from August 2020 to March 2021 were collected and observed. The patients were divided into an arrhythmia group and a control group according to whether there was arrhythmia in the 24 h ambulatory electrocardiogram examination report before operation. The incidence of intraoperative and postoperative cardiovascular events and short-term prognosis were compared between the two groups. Results A total of 466 patients were included in this study, including 338 patients in the arrhythmia group, 176 males and 162 females, with a median age of 68.0 (63.0, 72.0) years, and 128 patients in the control group, 59 males and 69 females, with a median age of 66.5 (60.0, 72.0) years. A total of 26 patients (7.7%) in the arrhythmia group were placed with temporary pacemakers before operation. There was no significant difference in the incidence of cardiovascular related events between the two groups [100 (29.6%) vs. 28 (21.9%), P=0.096]. The incidence of postoperative arrhythmia events in the arrhythmia group was higher than that in the control group [112 (33.1%) vs. 11 (8.6%), P<0.001]. The average postoperative ICU stay in the arrhythmia group was longer than that in the control group (1.1±0.7 d vs. 1.0±0.6 d, P=0.039). ConclusionPreoperative arrhythmia does not increase the risk of intraoperative cardiovascular events in NSCLC patients, but increases the incidence of postoperative arrhythmia events and prolongs ICU stay.
Objective To systematically review the effectiveness of amiodarone in treating repurfusion arrhythmia (RA) after thrombolytic therapy for acute myocardial infarction (AMI), so as to provide high quality evidence for formulating the rational thrombolytic therapy for AMI. Methods Randomized controlled trails (RCTs) on amiodarone in treating RA after thrombolytic therapy for AMI were electronically retrieved in PubMed, EMbase, The Cochrane Library (Issue 3, 2012), CBM, CNKI, VIP and WanFang Data from inception to January, 2013. According to the inclusion and exclusion criteria, two reviewers independently screened literature, extracted data, and assessed quality. Then RevMan 5.1 software was used for meta-analysis. Results A total of 5 RCTs involving 440 patients were included. The results of meta-analysis suggested that, compared with the blank control, amiodarone reduced the incidence of RA after thrombolytic therapy in treating AMI (RR=0.60, 95%CI 0.48 to 0.74, Plt;0.000 01) and the incidence of ventricular fibrillation (RR=0.47, 95%CI 0.26 to 0.85, P=0.01). It neither affected the recanalization rate of occluded arteries after thrombolytic therapy (RR=1.00, 95%CI 0.88 to 1.15, P=0.94) nor decreased the mortality after surgery (RR=0.33, 95%CI 0.10 to 1.09, P=0.07). Conclusion Current evidence indicated that, amiodarone can decrease the incidence of RA. Unfortunately, the mortality rate can’t be reduced by amiodarone. Due to the limited quality and quantity of the included studies, more high quality studies are needed to verify the above conclusion
Objective To explore how to differentiate the epilepsy and syncope in order to minimize the misdiagnosis. Methods Retrospectively analyzed the medical record of 6 cases which were misdiagnosed as epilepsy or syncope during April 2008 to September 2012 and reviewed the literatures about the differential diagnosis. Results Among the clinical characteristics, the ictal positional tone and loss of consciousness as well as the duration of postictal confusion are very important to the differential diagnosis. The ictal EEG shows highly rhythmic abnormal discharges when epileptic seizures occur. However, the ictal EEG would become slower and flatler during syncope. Conclusions When the automomic disorder and signs such as chest distress, arrhythmia. appear, the causes should not be limited in the cardiac diseases, the functional or structural abnormalities of the nervous system innervating the heart should also be considered; on the contrary, convulsions might not only due to the abnormal electrical activity in the brain, but syncope.
ObjectiveTo analyze the occurrence of arrhythmia in patients during the recovery period of anesthesia, in order to take appropriate measures in nursing care to ensure the safety of patients. Method We carried out a retrospective analysis of 18 931 general anesthesia post-operative patients (aged 16-84 years old) transferred to anesthesia recovery from September 2012 to July 2013, and we observed the incidence rate of arrhythmia, and documented the clinical manifestations of the patients. ResultsDuring the anesthesia recovery, out of 18 931 general anesthesia postoperative patients, 269 cases of arrhythmia occurred, and the incidence rate was 1.42%. Twenty minutes after nursing intervention and use of medication, the difference of systolic blood pressure, bradycardic heart rate, and tachycardic heart rate of the patients were statistically better than those beofre the treatment (P＜ 0.05) . ConclusionEarly discovery and analysis of arrhythmia in patients during anesthesia recovery, along with timely provision of analgesic and antiarrhythmic treatment can effectively improve the circulation status of the patients, thus ensure the safety of the patients during anesthesia recovery.
Deep learning method can be used to automatically analyze electrocardiogram (ECG) data and rapidly implement arrhythmia classification, which provides significant clinical value for the early screening of arrhythmias. How to select arrhythmia features effectively under limited abnormal sample supervision is an urgent issue to address. This paper proposed an arrhythmia classification algorithm based on an adaptive multi-feature fusion network. The algorithm extracted RR interval features from ECG signals, employed one-dimensional convolutional neural network (1D-CNN) to extract time-domain deep features, employed Mel frequency cepstral coefficients (MFCC) and two-dimensional convolutional neural network (2D-CNN) to extract frequency-domain deep features. The features were fused using adaptive weighting strategy for arrhythmia classification. The paper used the arrhythmia database jointly developed by the Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) and evaluated the algorithm under the inter-patient paradigm. Experimental results demonstrated that the proposed algorithm achieved an average precision of 75.2%, an average recall of 70.1% and an average F1-score of 71.3%, demonstrating high classification accuracy and being able to provide algorithmic support for arrhythmia classification in wearable devices.
ObjectiveTo investigate the clinical efficacy and safety of carvedilol in the treatment of arrhythmia in patients with hypertension complicated with diabetes mellitus. MethodsWe selected the patients with hypertension complicated with diabetes mellitus who were hospitalized in the Harrison International Peace Hospital Affiliated to Hebei Medical University for treatment from Oct. 2011 to Oct. 2013. The cases were divided into a trial group and a control group. The control group was given routine treatment (eg., hypoglycaemic drugs, angiotensin converting enzyme inhibitors). On the basis of the same treatment of the control group, the trial group was given carvedilol. The efficacy and adverse reaction were observed, recorded and then analyzed between the two groups. ResultsA total of 140 patients were included (70 cases in each group). With the loss of 10 cases in the control group, the data of 70 cases in the trial group and 60 cases in the control group were finally analyzed. The results showed that the trial group was superior to the control group in the total effectiveness (χ2=8.320, P=0.004) and the dynamic ECG improvement of premature ventricular contraction (χ2=5.333, P=0.014) with significant differences. Both groups were significantly improved in blood pressure and heart beats compared with the situation before treatment (Both P < 0.05), and the trial group was better than the control group with a significant difference. During the treatment, three cases in the trial group had mild gastrointestinal symptoms which spontaneously disappeared later. ConclusionThe clinical effectiveness of carvedilol for arrhythmia in patients with hypertension complicated with diabetes mellitus is significant. It is safe and effective which is recommended in clinical application.
ObjectiveTo systematically review the clinical efficacy of potassium magnesium aspartate in prevention of arrhythmia after cardiac heart surgery. MethodsSearching PubMed, MEDLINE, EMbase, The Cochrane Library (Issue 5, 2014), CNKI, VIP and WanFang Data to collect randomized controlled trials (RCTs) about the clinical efficacy of potassium magnesium aspartate in prevention of arrhythmia after cardiac heart surgery from the date of establishment of the databases to May 2014. Literature screening according to the inclusion and exclusion criteria, data extraction and methodological quality assessment of the included studies were completed by two reviewers independently. Meta-analysis was then conducted by RevMan 5.2 software. ResultsA total of nine RCTs involving 825 patients were enrolled. The results of meta-analysis indicated that: compared with the control group, timely giving supplement of potassium magnesium aspartate before and after surgery significantly reduced the incidences of arrhythmia (OR=0.25, 95%CI 0.09 to 0.69, P=0.008), premature beats (OR=0.08, 95%CI 0.03 to 0.23, P < 0.000 01), tachycardia (OR=0.29, 95%CI 0.17 to 0.49, P < 0.000 01) and 24 h low cardiac output (OR=0.27, 95%CI 0.10 to 0.72, P=0.009); and increased auto-resuscitation rates (OR=12.16, 95%CI 4.82 to 30.68, P < 0.000 01), with significant differences. However, the two groups were alike in the incidences of atrial fibrillation (OR=0.05, 95%CI-0.16 to 0.05, P=0.34) and ventricular fibrillation (OR=1.24, 95%CI 0.73 to 2.13, P=0.43). ConclusionPotassium magnesium aspartate is effective in prevention of arrhythmias after cardiac surgery, and protective to the myocardium. However, compared with conventional treatment it cannot significantly decrease the incidences of atrial fibrillation and ventricular fibrillation. Due to the limited quantity and quality of the included studies, more multi-centre high quality RCTs with large sample size are needed to verify the above conclusion.